Variable Species not found about ranger HOT 8 CLOSED

You have to specify your dependent variable name with --depvarname. In the example it was the iris dataset, where Species is the dependent variable.

from ranger.

Currently ranger is doing supervised learning, meaning you have to know the truth for your classification task. This truth will be your dependent variable for the training. I guess in your case this would be the true letters.

from ranger.

Please name the columns in your dataset in a header line. In addition, please code your outcome as numeric values.
Generally I would suggest to use the R version. These are all problems specific to the pure C++ version, which is not very optimised for usability. ;)

from ranger.

A dataset could look like this:

y x1 x2 x3
1 1.1 4.5 6.3
1 2.0 5.2 9.1
2 0.9 3.8 5.4
2 1.4 4.1 7.2
...

If y is your outcome and x1, x2, x3 are your predictors, you use --depvarname y.

This is probably not the right place for this question. I'm closing here, please post on Stack Overflow or the like.

from ranger.

Thanks for your reply. I still have some questions. For example , letter-recognization work, the train dataset is just numerical values,how can i make sure the dependent variable ? Or where is the "dependent variable" defined or used in the codes? I will very appreciate for your reply!

from ranger.

thans for your reply. my test work is supervised learing,which is letter-recognization.And train dataset's format is such as:
T,2,8,3,5,1,8,13,0,6,6,10,8,0,8,0,8
I,5,12,3,7,2,10,5,5,4,13,3,9,2,8,4,10
D,4,11,6,8,6,10,6,2,6,10,3,7,3,7,3,9
.......
the first column is label from A to Z,and others are characteristic。
How do I identify the --depvarname?
And I find the define of variable_name in the code <Data.cpp>
size_t Data::getVariableID(std::string variable_name) {
std::vectorstd::string::iterator it = std::find(variable_names.begin(), variable_names.end(), variable_name);
if (it == variable_names.end()) {
throw std::runtime_error("Variable " + variable_name + " not found.");
}
return (std::distance(variable_names.begin(), it));
}
so variable_name is vector?
I will very appreciate for your reply!

from ranger.

Hi,I am sorry to trouble you again,but i still have some questions.
First,I have read your codes, and find that train dataset label is on the first line in the dataset,and in the same column,it is characteristic under the first row.Are there any wrong ideas? For examplr:(I have replaced "A"with 1,"B" with 2,and so on)
A,B,C,F,G,............
1,3,5,6,9,............
3,5,8,3,4,............
.,.,.,.,.,............
.,.,.,.,.,............
Secondly,I still do not understand how to use --depvarname.In my work ,I have A~Z ,26 classes，then how to set this parameter.
I will very appreciate for your reply!

from ranger.

Thank you very much!

from ranger.